# Towards automatic construction of multi-network models for heterogeneous multi-task learning

## TL;DR

This paper introduces a formal framework for multi-network models capable of handling heterogeneous multi-task learning, demonstrated through an example involving classification, regression, and data sampling tasks.

## Contribution

It provides a formal definition of multi-network models for heterogeneous tasks and illustrates their potential with a practical example and analysis.

## Key findings

- The model can perform classification, regression, and data sampling tasks.
- Analysis shows the model's capabilities across different task types.
- Identifies open challenges and future directions for heterogeneous multi-task learning.

## Abstract

Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks. From classifying hand-written characters of different alphabets to figuring out how to play several Atari games using reinforcement learning, multi-task models have been able to widen their performance range across different tasks, although these tasks are usually of a similar nature. In this work, we attempt to widen this range even further, by including heterogeneous tasks in a single learning procedure. To do so, we firstly formally define a multi-network model, identifying the necessary components and characteristics to allow different adaptations of said model depending on the tasks it is required to fulfill. Secondly, employing the formal definition as a starting point, we develop an illustrative model example consisting of three different tasks (classification, regression and data sampling). The performance of this model implementation is then analyzed, showing its capabilities. Motivated by the results of the analysis, we enumerate a set of open challenges and future research lines over which the full potential of the proposed model definition can be exploited.